Dark Channel-Assisted Depth-from-Defocus from a Single Image

TL;DR

This paper introduces a novel single-image depth-from-defocus method that leverages the dark channel prior and adversarial training to estimate scene depth from a single defocused image, addressing the underconstrained nature of the problem.

Contribution

It proposes a new approach combining dark channel prior with end-to-end adversarial learning for single-image depth-from-defocus estimation, which was previously underexplored.

Findings

Dark channel prior improves depth estimation accuracy.

The method outperforms existing single-image DFD techniques.

Experiments validate the effectiveness of the approach on real data.

Abstract

We estimate scene depth from a single defocus-blurred image using the dark channel as a complementary cue, leveraging its ability to capture local statistics and scene structure. Traditional depth-from-defocus (DFD) methods use multiple images with varying apertures or focus. Single-image DFD is underexplored due to its inherent challenges. Few attempts have focused on depth-from-defocus (DFD) from a single defocused image because the problem is underconstrained. Our method uses the relationship between local defocus blur and contrast variations as depth cues to improve scene structure estimation. The pipeline is trained end-to-end with adversarial learning. Experiments on real data demonstrate that incorporating the dark channel prior into single-image DFD provides meaningful depth estimation, validating our approach.